Please wait a minute...
浙江大学学报（理学版）
浙江大学学报（理学版）  2020, Vol. 47 Issue (6): 715-723    DOI: 10.3785/j.issn.1008-9497.2020.06.009
地球科学     
基于多尺度学习与深度卷积神经网络的遥感图像土地利用分类
王协, 章孝灿, 苏程
浙江大学 地球科学学院 空间信息技术研究所，浙江 杭州 310027
Land use classification of remote sensing images based on multi-scale learning and deep convolution neural network
WANG Xie, ZHANG Xiaocan, SU Cheng
Institute of Spatial Information Technology,School of Earth Sciences，Zhejiang University,Hangzhou 310027,China
 全文: PDF(4229 KB)   HTML  
摘要： 土地利用信息是国土资源管理的基础和重要依据，随着高分辨率遥感图像数据的日益增多，迫切需要快速准确的土地利用分类方法。目前应用较广的面向对象的分类方法对空间特征的利用尚不够充分，在特征选择上存在一定的局限性。为此，提出一种基于多尺度学习与深度卷积神经网络（deep convolutional neural network，DCNN）的多尺度神经网络（multi-scale neural network，MSNet）模型，基于残差网络构建了100层编码网络，通过并行输入实现输入图像的多尺度学习，利用膨胀卷积实现特征图像的多尺度学习，设计了一种端到端的分类网络。以浙江省0.5 m分辨率的光学航空遥感图像为数据源进行了实验，总体分类精度达91.97%，并将其与传统全卷积网络（fully convolutional networks，FCN）方法和基于支持向量机（support vector machine，SVM）的面向对象方法进行了对比，结果表明，本文所提方法分类精度更高，分类结果整体性更强。
关键词： 土地利用分类;  多尺度学习;  深度卷积神经网络（DCNN）;  高分辨率遥感图像    
Abstract: Land use data is an important fundamental information for national land resources management. Following the availability of high resolution remote sensing image data, it is on urgent demand to have a fast and accurate land-use classification method. The object-oriented classification which has been widely applied at present has some problems such as low level utilization of spatial features and limited choice of features. In this paper, a multi-scale neural network (MSNet)model based on multi-scale learning and deep convolutional neural network (DCNN) is proposed. We built 100 layers encoding network based on residual neural network, and conducted several parallel input streams to accomplish multi-scale learning of input images, then utilized dilated convolution to accomplish multi-scale learning of feature images, finally designed an end-to-end classification network. Experiments were implemented on the optical aerial remote sensing images dataset of Zhejiang province with 0.5 m resolution, the overall accuracy of classification reached 91.97%. Compared with fully convolutional networks (FCN) network and the object-oriented method based on support vector machine (SVM), the MSNet method has a higher precision of classification and demonstrates more integrity of the scene.
Key words: high resolution remote sensing image    multi-scale learning    deep convolution neural network (DCNN)    land use classification
收稿日期: 2019-09-06 出版日期: 2020-11-25
CLC:  TP79  
作者简介: 王协(1990—)，ORCID: https://orcid.org/0000-0002-4392-9819，男，硕士，主要从事遥感数字图像处理研；
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　
王协
章孝灿
苏程

引用本文:

王协, 章孝灿, 苏程. 基于多尺度学习与深度卷积神经网络的遥感图像土地利用分类[J]. 浙江大学学报（理学版）, 2020, 47(6): 715-723.

WANG Xie, ZHANG Xiaocan, SU Cheng. Land use classification of remote sensing images based on multi-scale learning and deep convolution neural network. Journal of Zhejiang University (Science Edition), 2020, 47(6): 715-723.

链接本文:

https://www.zjujournals.com/sci/CN/10.3785/j.issn.1008-9497.2020.06.009    或    https://www.zjujournals.com/sci/CN/Y2020/V47/I6/715

1 王秀兰,包玉海.土地利用动态变化研究方法探讨[J].地理科学进展,1999,18(1):81-87.DOI:10.11820/dlkxjz.1999.01.012 WANG X L,BAO Y H.Study on the methods of land use dynamic change research[J].Progress in Geography,1999,18(1): 81-87. DOI:10.11820/dlkxjz.1999.01.012
2 杨志荣,吴次芳,刘勇,等.快速城市化地区生态系统对土地利用变化的响应——以浙江省为例[J].浙江大学学报(农业与生命科学版),2008,34(3):341-346.DOI:10.3785/j.issn.1008-9209.2008.03.017 YANG Z R,WU C F,LIU Y,et al.Research on response of ecosystem to changes in land use in rapid urbanization areas-A case study of Zhejiang province[J].Journal of Zhejiang University(Agric & Life Sci),2008,34(3):341-346.DOI:10.3785/j.issn.1008-9209.2008.03.017
3 张兵.当代遥感科技发展的现状与未来展望[J].中国科学院院刊,2017,32(7):774-784.DOI:10.16418/j.issn.1000-3045.2017.07.012 ZHANG B.Current status and future prospects of remote sensing[J].Bulletin of Chinese Academy of Sciences,2017,32(7):774-784.DOI:10.16418/j.issn.1000-3045.2017.07.012
4 RICHARDS J A,RICHARDS J A.Remote Sensing Digital Image Analysis[M].Berlin:Springer,1999.DOI:10.1007/ 978-3-662-03978-6
5 BAATZ M,SCHÄPE A.Multiresolution segmentation:An optimization approach for high quality multi-scale image segmentation[C]// Proceedings of the Beiträge Zum AGIT-Symposium.Karlsruhe: Herbert Wichmann Verlag，2000：12-23.
6 ZHAO W,DU S,EMERY W J.Object-based convolutional neural network for high-resolution imagery classification[J].IEEE Journal of Selected Topics in Applied Earth Observations & Remote Sensing,2017(99):1-11.DOI:10.1109/JSTARS. 2017.2680324
7 HINTON G E,OSINDERO S,TEH Y.A fast learning algorithm for deep belief nets[J].Neural Computation,2006,18(7):1527-1554.DOI: 10.1162/neco.2006.18.7.1527
8 HINTON G E,SALAKHUTDINOV R R.Reducing the dimensionality of data with neural networks[J].Science,2006,313(5786):504-507.DOI:10.1126/science.1127647
9 LECUN Y,BENGIO Y,HINTON G.Deep learning[J].Nature,2015,521(7553):436-444.DOI:10.1038/nature1453 9
10 REN S，HE K，GIRSHICK R，et al.Faster R-CNN：Towards real-time object detection with region proposal networks［C］//Proceedings of the 28th International Conference on Neural Information Processing Systems. Cambridge：MIT Press，2015：91-99. DOI：10.1109/TPAMI.2016.2577031
11 CHEN L C,PAPANDREOU G,KOKKINOS I,et al.DeepLab:Semantic image segmentation with deep convolutional nets,atrous convolution,and fully connected CRFs [J].IEEE Transactions on Pattern Analysis & Machine Intelligence,2018,40(4):834-848. DOI:10.1109/TPAMI.2017.2699184
12 LE Q V，RANZATO M A，MONGA R，et al.Building high-level features using large scale unsupervised learning［C］//2013 IEEE International Conference on Acoustics,Speech and Signal Processing.Vancouver：IEEE，2013.DOI：10.1109/ICASSP.2013.6639343
13 KRIZHEVSKY A，SUTSKEVER I，HINTON G E.ImageNet classification with deep convolutional neural networks［J］.Communications of the ACM，2017，60（6）：84-90. DOI：10.1145/3065386
14 SHERRAH J.Fully convolutional networks for dense semantic labelling of high-resolution aerial imagery[EB/OL].https://arXiv.org/abs/1606.02585（2016-1-8）
15 SIMONYAN K，ZISSERMAN A.Very deep convolutional networks for large-scale image recognition［EB/OL］//https：//arXiv.org/abs/2014 arXiv1409.15568（2014-9-4）.
16 VOLPI M,TUIA D.Dense semantic labeling of sub-decimeter resolution images with convolutional neural networks[J].IEEE Transactions on Geoscience and Remote Sensing,2016,55(2):881-893.DOI:10.1109/TGRS.2016.2616585
17 ZHU Q,ZHONG Y,BEI Z,et al.Bag-of-visual-words scene classifier with local and global features for high spatial resolution remote sensing imagery[J].IEEE Geoscience & Remote Sensing Letters,2017,13(6): 747-751. DOI:10.1109/LGRS.2015.2513443
18 LUO W，LI Y，URTASUN R，et al.Understanding the effective receptive field in deep convolutional neural networks［C］//Proceedings of the 30th International Conference on Neural Information Processing Systems.Red Hook：Curran Associates Inc，2016： 4905-4916.
19 SHELHAMER E，LONG J，DARRELL T.Fully convolutional networks for semantic segmentation ［J］.IEEE Transactions on Pattern Analysis and Machine Intelligence，2017，39（4）：640-651. DOI：10.1109/TPAMI.2016.2572683
20 HE K M,ZHANG X Y,REN S Q,et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas：IEEE,2016. DOI:10.1109/CVPR.2016.90
21 IOFFE S，SZEGEDY C.Batch normalization：Accelerating deep network training by reducing internal covariate shift［C］//Proceedings of the 32nd International Conference on Machine Learning.Cambridge：MIT Press，2015.
22 YOSINSKI J，CLUNE J，BENGIO Y，et al.How transferable are features in deep neural networks？［C］//Proceedings of the 27th International Conference on Neural Information Processing Systems.Cambridge：MIT Press，2014: 3320-3328.
[1] 吴郁文,林杰. 融合遥感与社会感知数据的城市土地利用分类方法[J]. 浙江大学学报（理学版）, 2023, 50(1): 83-95.